Index
Partial Convolution for CT Field of View Extension
Diffusion Model-Enabled Energy Level Transformation in Photon Counting Computed Tomography (PCCT)
Introduction:
Photon counting computed tomography (PCCT) marks a new era in medical imaging, offering an unprecedented ability to discriminate between different photon energy levels. This feature of PCCT is crucial for enhancing image contrast and specificity, allowing for more accurate tissue characterization. However, efficiently managing and converting between these diverse energy levels in a clinically practical manner remains a significant challenge.
This project aims to utilize diffusion model to streamline and optimize the energy level conversion process in PCCT. By leveraging the advanced pattern recognition and computational capabilities of diffusion model, the project intends to develop a system that can automatically and accurately translate between different photon energy levels, enhancing the utility and clarity of PCCT images.
The ultimate goal is to provide a robust and efficient framework that not only improves the diagnostic quality of PCCT images but also expands the practical applications of this technology in clinical settings. This involves intricate work in both the development of diffusion model and the understanding of the physics underlying PCCT.
Requirements:
- Completion of Deep Learning is mandatory.
- Proficiency in PyTorch is essential.
- Strong analytical and problem-solving skills.
Prospective candidates are warmly invited to send their CV and transcript to yipeng.sun@fau.de.
A Bias Analysis on Audio and Linguistic Embeddings for the Classification of Alzheimer’s Disease
Deep Learning for Glioma Survival Prediction
Estimation of 3D Implant Pose and Position from 2D X-Ray Images using Transformer Networks
Deep Learning for Bias Field Correction in MRI Scans
Spoken Language Identification for Hearing Aids
Development of a Gamification Platform for Wildlife Identification and Understanding
MASTER’S PROJECT (10 ECTS)
Multiple people required!
Welcome to “FinLearn” – an innovative gamification platform aimed at unraveling the mysteries of killer whales through photo identification, engaging users of all ages in an immersive learning experience. As developers, you have the opportunity to shape this platform into a captivating educational tool that inspires curiosity and fosters understanding about these majestic creatures.
FinLearn leverages state-of-the-art deep learning algorithms to analyze vast collections of killer whale images, allowing users to explore their distinctive markings, behaviors, and ecological roles. Through interactive modules and challenges, users embark on a captivating journey, learning about orca social dynamics, migration patterns, and the importance of conservation efforts.
Your role as developers is crucial in crafting engaging quests, challenges, and interactive elements that bring the world of killer whales to life. Whether it’s annotating photo identifications, analyzing behavioral cues, or exploring virtual marine environments, your creativity and expertise will shape the user experience and inspire a sense of wonder and discovery.
Furthermore, FinLearn fosters collaboration and community engagement, providing users with opportunities to share insights, discuss findings, and collaborate on research projects. By integrating discussion forums, collaborative initiatives, and leaderboards, you can create a vibrant learning community that transcends age barriers and geographical boundaries.
Together, let’s embark on this exciting journey of exploration and conservation. With FinLearn, you have the power to ignite a passion for marine science and conservation in users of all ages, inspiring a new generation of stewards committed to protecting the future of killer whales and their ocean habitats.
Project Requirements:
Required: Programming experience.
Nice to have: Experience in .NET, Angular, database design, web design, and familiarity with microservice architectures (Kubernetes, Docker)